Orthopedic 3D printing model construction method and device based on intelligent AI

Abstract

The invention discloses an orthopedic 3D printing model construction method and device based on intelligent AI, and relates to the technical field of image.The method comprises the steps that a user database is collected, an image imaging scheme is configured, multi-view imaging is executed, and a DICOM format image data set is established; placing an image data set in the three-dimensional coordinate system and establishing registration mapping; after the image data set is preprocessed, skeleton segmentation is executed, and the segmentation trust degree is identified; carrying out image fusion reconstruction according to the registration mapping and the segmentation credibility, and generating a three-dimensional model for identifying the position complexity; printing placement fitting is carried out based on the three-dimensional model, the gravity direction is determined, and the geometrical shape is analyzed to determine a preliminary supporting area; according to the position complexity and the initial support area optimization support point, establishing a selection optimization result; and optimizing the three-dimensional model according to a selection optimization result, and generating an orthopedic 3D printing model of the user. Therefore, the technical effects of improving the modeling efficiency and precision and improving the printing stability are achieved.

Description

Technical Field

[0001] The present invention relates to the field of image technology, and in particular to an orthopedic 3D printing model construction method and device based on intelligent AI. Background Art

[0002] The application of 3D printing technology in the medical field, especially in orthopedic surgery, can help doctors observe the patient's bone structure more intuitively, conduct preoperative planning and simulation, and improve the accuracy and success rate of surgery. The existing orthopedic 3D printing model construction method usually relies on fixed parameter modes, supplemented by manual operation, and has technical problems such as long modeling time, low accuracy, and poor printing stability. Summary of the invention

[0003] The present invention provides an orthopedic 3D printing model construction method and device based on intelligent AI to solve the technical problems of long modeling time, low precision and poor printing stability in the prior art, and achieve the technical effect of improving modeling efficiency and precision and enhancing printing stability.

[0004] In a first aspect, the present invention provides an orthopedic 3D printing model construction method based on intelligent AI, wherein the method comprises: Acquire the user database of the user, configure the imaging scheme based on the user database, perform multi-view imaging of the user based on the imaging scheme, establish an image data set, and save the image data set in DICOM format; establish a three-dimensional coordinate system, place the image data set into the three-dimensional coordinate system, perform image registration with the image coordinates in the three-dimensional coordinate system, and establish a registration mapping; after preprocessing the image data set, perform bone segmentation of the preprocessed image data set, and establish a segmentation result, wherein the segmentation result carries a segmentation confidence mark; perform image fusion reconstruction according to the registration mapping and the segmentation confidence mark, generate a three-dimensional model, and identify the position complexity of the three-dimensional model; perform printing placement fitting based on the three-dimensional model, determine the direction of gravity, perform geometric shape analysis of the three-dimensional model with the direction of gravity, and determine the preliminary support area; perform support point selection optimization based on the position complexity and the preliminary support area, and establish a selection optimization result; optimize the three-dimensional model according to the selection optimization result, and establish the user's orthopedic 3D printing model.

[0005] In a second aspect, the present invention also provides an orthopedic 3D printing model construction device based on intelligent AI, wherein the device comprises: An image data acquisition module is used to acquire a user database of a user, configure an image imaging scheme based on the user database, perform multi-view imaging of the user based on the image imaging scheme, establish an image data set, and save the image data set in DICOM format.

[0006] A three-dimensional registration module is used to establish a three-dimensional coordinate system, place the image data set into the three-dimensional coordinate system, perform image registration with the image coordinates in the three-dimensional coordinate system, and establish a registration mapping.

[0007] The bone segmentation module is used to perform bone segmentation on the preprocessed image data set after preprocessing the image data set, and establish a segmentation result, wherein the segmentation result carries a segmentation confidence mark.

[0008] A fusion reconstruction identification module is used to perform image fusion reconstruction according to the registration map and the segmentation confidence identification, generate a three-dimensional model, and identify the position complexity of the three-dimensional model.

[0009] A placement support module is used to perform printing placement fitting based on the three-dimensional model, determine the direction of gravity, perform geometric shape analysis of the three-dimensional model based on the gravity direction, and determine a preliminary support area.

[0010] A support optimization module is used to select and optimize support points based on the position complexity and the preliminary support area, and establish a selection optimization result.

[0011] The entity execution module is used to optimize the three-dimensional model according to the selection optimization result and establish an orthopedic 3D printing model for the user.

[0012] The present invention discloses an orthopedic 3D printing model construction method and device based on intelligent AI, comprising: collecting and acquiring user database information of a user, formulating an imaging scheme based on the database, executing multi-view imaging of the user, generating an image data set, and saving the image data set as a DICOM format file; establishing a three-dimensional coordinate system, placing the image data set in the coordinate system, and performing image registration with the image coordinates in the three-dimensional coordinate system to form a registration mapping relationship; preprocessing the image data set, and performing a bone segmentation operation in the preprocessed image to generate a segmentation result, the segmentation result having a segmentation confidence mark; fusing and reconstructing the image according to the registration mapping and the segmentation confidence mark to generate a three-dimensional model, and marking the spatial position complexity of the three-dimensional model; performing print placement fitting on the three-dimensional model, determining the gravity direction, performing geometric shape analysis based on the gravity direction, and determining a preliminary support area; optimizing and selecting support points based on the position complexity and the preliminary support area, and generating a selection optimization result; optimizing the three-dimensional model according to the selection optimization result, and finally generating the user's orthopedic 3D printing model. The intelligent AI-based orthopedic 3D printing model construction method and device disclosed in the present invention solve the technical problems of long modeling time, low precision, and poor printing stability, and achieves the technical effect of improving modeling efficiency and precision and enhancing printing stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 The figure is a flow chart of the method for constructing an orthopedic 3D printing model based on intelligent AI of the present invention.

[0014] Figure 2 This is a schematic diagram of the structure of the orthopedic 3D printing model construction device based on intelligent AI of the present invention.

[0015] Explanation of the accompanying drawings: image data acquisition module 11, three-dimensional registration module 12, bone segmentation module 13, fusion reconstruction identification module 14, placement support module 15, support optimization module 16, entity execution module 17. DETAILED DESCRIPTION

[0016] The technical solution provided in the embodiments of the present invention is to solve the technical problems of long modeling time, low precision and poor printing stability in the prior art. The overall idea adopted is as follows: First, collect and obtain the user's user database, which contains the user's basic information and medical image data. Based on the user database, configure the imaging solution, which may include image acquisition methods of different angles, such as CT, MRI, etc.

[0017] Then, based on the configured imaging scheme, the user is imaged from multiple perspectives, and the collected image data set will be saved in DICOM format for subsequent processing and analysis. Next, a three-dimensional coordinate system is established, and the collected image data set is placed in the three-dimensional coordinate system. The image coordinates are used for image registration to ensure that images from different perspectives can correctly correspond and map to form a registration mapping relationship. After the image data set is preprocessed, the bone segmentation operation is performed to extract the structural information of the bone, and the trust of each segmentation result is marked, that is, the accuracy of each segmentation area. According to the registration mapping and segmentation trust, the images from different perspectives are fused and reconstructed to generate the user's three-dimensional bone model. At the same time, based on the segmentation results and image complexity, the position complexity of the three-dimensional model is identified, which is crucial for the selection of support points and 3D printing. After that, based on the generated three-dimensional model, the printing placement is fitted, the gravity direction during the printing process is determined, and the geometric shape analysis is performed to identify the areas that may need support and determine the preliminary support area. Next, combined with the position complexity of the three-dimensional model and the preliminary support area, the support points are optimized to find the most suitable support point layout and generate the optimization results of the support point selection. Finally, based on the optimization results of the support points, the 3D model is optimized and the user's orthopedic 3D printing model is finally generated. This model will be used for surgical planning, prosthesis design or other orthopedic related applications.

[0018] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention are shown in the drawings, rather than all of them.

[0019] Embodiment 1 Figure 1 The figure is a flow chart of the method for constructing an orthopedic 3D printing model based on intelligent AI of the present invention, wherein the method comprises: Acquire a user database of the user, configure an imaging scheme based on the user database, perform multi-view imaging of the user based on the imaging scheme, establish an image data set, and save the image data set in DICOM format.

[0020] Specifically, the user database is first interacted with to obtain the user data of the target user, which reflects the user characteristic information of the target user and is used to provide a reference for imaging. For example, the user database includes data such as the user's body shape, posture, position to be modeled, and modeling accuracy requirements.

[0021] Specifically, the imaging scheme is configured based on the user database. First, relevant information is extracted from the user database, such as the user's bone position, body shape, posture, gender, age, etc., as the basic data for formulating the imaging scheme; then, the specific requirements for imaging are determined according to the user's health status or bone needs. For example, whether it is necessary to focus on certain parts, whether there are specific imaging angles or resolution requirements, etc. Next, the parameters of the imaging device are adjusted according to the user's body structure data (such as bone position and body shape) to ensure that the parts of interest that need to be collected are covered, and to provide a collection clarity that meets the resolution requirements. The parameters of the imaging device include the device position (height and distance of the imaging device), imaging angle, radiation dose, etc. Through the above steps, it is ensured that the imaging scheme is adapted to the user's personalized needs and physical characteristics, so as to obtain clear and accurate images.

[0022] Furthermore, the user is imaged from multiple perspectives according to the imaging scheme. The user's image data is captured from different angles and directions to ensure that comprehensive and accurate image information is obtained. Exemplarily, the user is photographed from multiple angles such as front, back, left, right, and oblique, and all the captured image data are sorted and organized according to the imaging order or the view order to establish a complete image data set. The image data set contains images from all viewpoints to ensure that the target area can be completely reconstructed and observed from multiple perspectives in subsequent analysis.

[0023] Specifically, the processed image dataset is converted and saved in DICOM (Digital Imaging and Communications in Medicine) format. DICOM files contain necessary user information (such as name, ID), imaging device parameters, imaging time, and other related metadata for subsequent access, call, and analysis.

[0024] A three-dimensional coordinate system is established, the image data set is placed in the three-dimensional coordinate system, image registration is performed with the image coordinates in the three-dimensional coordinate system, and a registration mapping is established.

[0025] Specifically, first, a three-dimensional coordinate system is established as the reference system of the image data. This coordinate system is based on the physical position of the device, the center point of the imaging part, or other space with fixed reference points, and each axis of the three-dimensional coordinate system represents the X, Y, and Z directions, so that the position of each image in the three-dimensional space can be accurately located.

[0026] Specifically, the image data set obtained from multi-view imaging is read, and the initial position and direction in the three-dimensional coordinate system are determined according to the specific viewing angle, position information and imaging time of the imaging device corresponding to each image data, and each image is placed in the three-dimensional coordinate system according to its position information.

[0027] Specifically, the multi-view image data in the above three-dimensional coordinate system is the initial image data restored according to the acquisition direction. In actual acquisition, due to changes in user posture or movement, there are imperfect fits between the multi-angle image data, and it is difficult to form accurate bone image data. Therefore, further image registration is required to align images from different perspectives and establish a consistent three-dimensional model. The purpose of registration is to correct the differences in position, rotation, scaling, etc. between multi-view images through a transformation matrix. Exemplarily, image registration in a three-dimensional coordinate system is performed based on registration algorithms such as RANSAC, 4PCE, and IPC.

[0028] Exemplarily, first, extract key feature points shared with adjacent images from each image. Feature points can be determined based on physical structures, edges, textures or other significant features in the image. Then, use the 4PCS algorithm to extract a set of four points from images of different perspectives, and the geometric relationship of these four points in the image remains consistent. Then, compare the spatial positions of the point sets in adjacent images to obtain the similarity transformation between the images. Finally, match these key point sets and solve the optimal rigid body transformation matrix (including rotation, translation and scaling). This matrix will be used to transform one of the images so that it is aligned with images from other perspectives.

[0029] Furthermore, after obtaining the optimal transformation matrix, the matrix is ​​applied to transform the image, and all image data sets are registered so that they are aligned to the same reference frame in the three-dimensional coordinate system, and a registration mapping relationship is established for each image. The registration mapping relationship records the original position of each image, the transformation matrix after registration, and their coordinate positions in three-dimensional space.

[0030] After preprocessing the image data set, skeleton segmentation of the preprocessed image data set is performed to establish a segmentation result, wherein the segmentation result carries a segmentation confidence mark.

[0031] Specifically, Google segmentation is used to segment the bone region in the preprocessed image dataset from other tissues (such as muscle, fat, etc.). Segmentation methods include threshold segmentation, region growing, level set method, deep learning method, etc.

[0032] Exemplarily, convolutional neural networks (CNNs) are also widely used in image segmentation tasks. First, prepare a set of labeled training data, such as a set of CT images, and corresponding bone segmentation labels. The labeled labels are Boolean values, which are used to indicate whether each pixel belongs to a bone. Then, the training data is used to train the CNN. It involves forward propagation, back propagation, and parameter updates (such as stochastic gradient descent to update network parameters). After the network training is completed, it can be used to perform bone segmentation on new CT images and output the segmentation results with segmentation confidence marks. In other words, the preprocessed image is input into the network, and the network outputs a segmented image (segmentation result), in which the value of each pixel represents the probability that the pixel belongs to the bone (segmentation confidence).

[0033] Through the above method steps, the bone segmentation of the image data set is performed, which helps to accurately identify the pixels belonging to the bones in the image data, thereby improving the accuracy of subsequent three-dimensional model construction.

[0034] Image fusion reconstruction is performed according to the registration mapping and the segmentation confidence mark to generate a three-dimensional model, and the position complexity of the three-dimensional model is marked.

[0035] Specifically, based on the established registration mapping, the multi-view image data is aligned to a unified three-dimensional coordinate system. Through these registration mappings, the bone regions of each view image can be accurately mapped to the same three-dimensional spatial position; then, the segmentation results of each view are weighted using the segmentation confidence mark, where the part with a higher segmentation confidence will occupy a larger weight in the three-dimensional model, thereby improving the reliability and accuracy of the model. Next, the segmented bone images of each view are fused.

[0036] Optionally, a voxel-level fusion method is used to combine the segmentation results of each view to eliminate the imperfect fitting problem caused by the user's posture or movement changes, and the fused image data is converted into three-dimensional voxel data.

[0037] Optionally, based on the voxel data, a grid structure of a three-dimensional model is generated using Marching Cubes or other surface reconstruction algorithms to present the bone structure in the form of a three-dimensional geometric model. Preferably, in the generated three-dimensional model, smoothing, denoising or hole filling are adaptively performed to improve the accuracy and quality of the model.

[0038] Specifically, the complexity of different parts of the model is quantified through methods such as curvature analysis, shape complexity analysis or density analysis to obtain the positional complexity of multiple positions. Among them, parts with higher complexity mean that these areas are more prone to errors in the actual imaging or reconstruction process, and are more difficult to print in the subsequent 3D printing process, requiring refined support settings and printing slices.

[0039] Through the above steps, a high-precision three-dimensional bone model with clear position complexity can be generated, providing a reliable model basis for subsequent printing analysis and planning.

[0040] In some embodiments, performing image fusion reconstruction according to the registration map and the segmentation confidence identifier further includes: The weights are configured according to the registration map, as follows: ; in, Characterize the registration mapping The weight of the image from each view, Characterization The image quality score of the image from each perspective is Characterization The segmentation confidence level of each view image is Characterizes the number of viewpoints corresponding to the registration map, The perspective index.

[0041] Pixel fusion is performed according to the configured weights as follows: ; Represents the pixel value after fusion, For the The pixel value of the corresponding position of the perspective image.

[0042] Image fusion reconstruction is completed based on the fused pixel values.

[0043] Optionally, before image fusion and reconstruction, a corresponding weight is assigned to the image of each perspective, and the weight depends on the quality of the image and the confidence of the segmentation. Specifically, first, based on the above-mentioned weight configuration formula, the weight of the fusion of multiple perspective images is calculated, wherein the higher the image quality and the larger the segmentation confidence mark, the higher the corresponding weight; then, pixel fusion is performed according to the configured weight. Specifically, the fusion value of each pixel position is obtained by the weighted average of all pixel values ​​at the corresponding position and their weights, ensuring that pixels of images with high quality and good segmentation confidence are given priority. Finally, the fused multi-perspective images are stacked to generate a three-dimensional image or pixel fusion is performed directly in three-dimensional space to complete the image fusion reconstruction. The above steps can ensure that the image fusion process takes into account the quality and confidence of each perspective image, thereby generating a more accurate fusion result.

[0044] In some implementations, performing image fusion reconstruction according to the registration map and the segmentation confidence identifier to generate a three-dimensional model and identifying the position complexity of the three-dimensional model further includes: Extract the amount of fused data for image fusion reconstruction, perform adaptation evaluation based on the fused data amount and the position complexity, and establish an adaptation abnormality flag; generate an additional acquisition instruction based on the adaptation abnormality flag; control the imaging device to perform additional data acquisition through the additional acquisition instruction, and perform image fusion reconstruction compensation based on the additional data acquisition result.

[0045] Specifically, based on a three-dimensional sliding window, the amount of fused data and the corresponding positional complexity of multiple positions of the three-dimensional model are extracted by sliding, wherein the three-dimensional sliding window is a stereoscopic space of a preset size, which can be a finite space of a size determined in the three-coordinate direction or an interval space in any two coordinates or any single coordinate direction, determined based on the shape characteristics of the target skeleton. Then, the positional complexity corresponding to the acquired fused data volume is calculated, including the sum of the complexity of multiple unit parts of the three-dimensional model between the three-dimensional sliding windows. Furthermore, based on the acquired fused data volume and the corresponding positional complexity, an adaptation evaluation is performed. If the ratio of the fused data volume to the positional complexity does not meet the preset adaptation constraints, an adaptation abnormality flag is generated.

[0046] Exemplarily, if the ratio of the amount of fused data to the location complexity is less than the lower limit of the preset adaptation constraint, the amount of fused data at the location is too small relative to its complexity, the modeling quality of the area is insufficient, and more data is needed to provide a more accurate reconstruction.

[0047] Furthermore, an additional acquisition instruction is generated according to the adaptation abnormality mark to instruct the imaging device to collect more data in the corresponding area of ​​the adaptation abnormality mark, and image fusion and reconstruction are performed again according to the acquired additional data acquisition results to improve the image quality of this position.

[0048] Through the above method steps, the complexity of the position can be combined to effectively ensure the quality balance of the three-dimensional model after image fusion and reconstruction at different positions, avoid reconstruction errors caused by insufficient data at complex positions, and ensure that there is sufficient data at all positions for accurate image fusion and reconstruction, thereby improving the final image quality.

[0049] Printing placement fitting is performed based on the three-dimensional model to determine the direction of gravity, and the geometric shape analysis of the three-dimensional model is performed based on the direction of gravity to determine the preliminary support area.

[0050] Specifically, first, the generated 3D model is placed in a virtual printing environment, the printing position and angle of the model are simulated, and the optimal placement angle and direction of the model on the printing platform are determined by fitting analysis to ensure the stability of the model and minimize support requirements during the printing process.

[0051] Specifically, after fitting is completed, the gravity direction of the model is determined, that is, the direction of gravity during the actual printing process, which helps to determine the force conditions and potential deformation areas of the model during printing.

[0052] Specifically, the analysis is performed based on the geometry of the 3D model and the direction of gravity. The focus is on identifying areas in the model that may be deformed due to gravity or require additional support. Examples include protrusions, suspended parts, surfaces with large inclination angles, and complex structures.

[0053] Among them, the preliminary support area of ​​the model is determined based on the results of the geometric shape analysis. The preliminary support area is used to provide additional support during the printing process to prevent the model from collapsing or deforming due to gravity or structural fragility. In addition, the selection of the support area will also consider how to reduce the difficulty of removing the support after printing, thereby optimizing printing efficiency.

[0054] Based on the position complexity and the preliminary support area, support points are selected and optimized, and selection optimization results are established.

[0055] In some embodiments, the selecting and optimizing support points based on the position complexity and the preliminary support area and establishing the selection and optimization result further includes: Each preliminary support area is taken as an independent area, and a regional objective function is established based on the regional information of the preliminary support area, and the evaluation characteristics of the regional objective function include the number of support points, materials, stability, and post-processing difficulty; regional evaluation is performed on the independent area, and regional associations of independent areas are established, and the regional associations include regional collaborative associations and regional competitive associations, and the regional evaluation includes spatial proximity analysis, mechanical coupling analysis, and material sharing analysis; limit constraints of support points are established, and the solution space is configured with the limit constraints. The regional objective function is used as the evaluation function, and the selection optimization of support points is executed in the solution space, and iterative compensation of the selection optimization is performed through regional association to establish the selection optimization result.

[0056] Specifically, the rating indicators for the preliminary support area include the number of support points, materials, stability, and post-processing difficulty. Among them, the fewer the number of support points, the smaller the corresponding support contact area, and the smaller the impact on the surface quality of the model; correspondingly, the less material consumption, the less waste generated by removing the support; stability is another important factor in evaluating the support structure. The support structure should be able to maintain the stability of the model throughout the printing process to prevent it from moving or collapsing. Exemplarily, the stability is determined based on the rigidity of the support structure and the firmness of the connection between the support structure and the model body; post-processing includes steps such as removing the support structure and cleaning and repairing the model surface. If the support structure is designed to be too complex or difficult to remove, the difficulty of post-processing will increase, which will increase manufacturing time and cost.

[0057] Specifically, multiple independent regions may have synergistic relationships (i.e., they work together in some way) or competitive relationships (i.e., they conflict in resources or space). By performing spatial proximity analysis, mechanical coupling analysis, and material sharing analysis on multiple independent regions, the regional relationships of independent regions can be obtained.

[0058] Among them, spatial proximity analysis is used to evaluate the spatial relationship between various areas, such as the distance and relative position between independent areas. It helps to determine which areas may need to share support structures, or which areas' printing may affect each other. Mechanical coupling analysis is used to evaluate the mechanical interactions that may occur in various areas during the printing process, such as stress, deformation, etc. It helps to determine the support structure for the foreman to withstand these forces, and predict possible printing problems. Material sharing analysis is used to evaluate the material requirements of each area during the printing process, as well as possible material sharing strategies. For example, if two adjacent independent areas have the same or similar orientations, a strategy for sharing support structures can be designed to improve the stability of the support, reduce material usage and printing time. Through the above evaluation, the influence relationship between different independent areas is established, which helps to optimize the 3D printing process, improve efficiency, reduce costs, and improve printing quality.

[0059] Optionally, the limit constraints are restrictions imposed on the variables in the optimization problem, defining the boundaries of the solution space. Exemplarily, the limit constraints include the size of the printing platform, the support form (such as tree, geometric curve, hybrid, etc.), the support spacing, the support generation threshold, etc. The solution space is a set of all possible solutions. After setting the limit constraints, the solution space represents the area restricted by these constraints. Preferably, the characteristics of the solution space are described in combination with the graphical representation and the mathematical model. By setting the limit constraints and configuring the solution space, the scope of the optimization problem can be effectively narrowed and the solution efficiency can be improved.

[0060] In some implementations, the iterative compensation for selecting optimization through regional association further includes: Establish collaborative grouping and competitive grouping based on the regional association; construct a joint objective function through the regional objective function corresponding to the collaborative grouping, and perform joint optimization of the collaborative grouping based on the joint objective function; sort the competitive groups in order of priority and establish a sorting result; establish sequential optimization based on the sorting result, and complete iterative compensation according to the joint optimization and sequential optimization.

[0061] Specifically, first, according to the relationship between regions, multiple independent spaces are divided into collaborative groups and competitive groups. Multiple collaborative groups include multiple groups of independent spaces with synergistic relationships, such as multiple model branches hanging to the same side; competitive groups include multiple independent spaces with competitive relationships, such as multiple model branches hanging in opposite directions or model parts that conflict in space or resources, or their printing order may affect the efficiency and quality of printing. Specifically, a joint objective function is constructed based on the objective function of the collaborative grouping to obtain a printing strategy that maximizes these synergistic effects. Then, the regions of the competitive grouping are prioritized, and then optimization is performed based on the ranking results, including, for example, deciding which regions should be printed first and how to arrange the printing order to minimize conflicts and resource waste.

[0062] Furthermore, according to the results of the above joint optimization and sequential optimization, iterative compensation is performed to further improve printing efficiency and quality by adjusting printing parameters or modifying support design. The above method steps understand the complexity of the model to obtain the optimal printing strategy by considering the relationship and interaction between various regions and their impact on the overall goal.

[0063] The three-dimensional model is optimized according to the selection optimization result to establish an orthopedic 3D printing model for the user.

[0064] In some embodiments, the method further comprises: The three-dimensional model is subjected to fixed-point position recognition, and scale division is performed based on the fixed-point position recognition result to establish M scale division results; spatial scale filtering from coarse scale to fine scale is performed based on the M scale division results; after all scale division results are filtered, filtering fusion of each scale division result is performed, and the three-dimensional model is updated according to the filtering fusion result.

[0065] Specifically, first, the key points or feature points of the 3D model are identified as fixed-point locations for scale division, and the scale division result is obtained, which includes a series of sub-models or regions, each of which has its own scale or resolution. For example, some parts of the model may be divided into coarse scales (low resolution), while other parts may be divided into fine scales (high resolution). Exemplarily, the fixed-point locations include curvature discontinuity points, curvature mutation points, complexity mutation points, etc.

[0066] Specifically, the result of each scale division is filtered to eliminate noise, smooth data, optimize the geometry and structure of each scale division to improve printing efficiency and quality. Preferably, filtering is performed by adaptive parameter adjustment to process different parts of the model at different scales, thereby adapting to the complexity and diversity of the model.

[0067] For example, the filter parameters are adjusted according to the curvature or complexity of different parts of the model to optimize the printing effect of each part. For the coarse-scale (smaller curvature or less complex) parts of the model, larger filter parameters are used to smooth large geometric shapes or structures; while for the fine-scale (larger curvature or more complex) parts of the model, smaller filter parameters are used to retain details, thereby improving the printing quality of the model and the printing efficiency.

[0068] Furthermore, the filtering results of all scale divisions are fused together, and then the 3D model is updated according to the fusion results to achieve the best printing effect. Through the above method steps, the 3D model is analyzed and optimized at multiple scales by combining feature point analysis and filtering methods, thereby improving printing efficiency and quality.

[0069] In some implementations, performing spatial scale filtering from a coarse scale to a fine scale based on the M scale division results further includes: The spatial scale filtering is performed through the formula as follows: ; in, Represents a vertex The new position vector after filtering is Vertex The original position vector, is the smoothing coefficient, Characterizing Vertices The set of adjacent vertices of Characterizing Vertices Any adjacent vertex of Vertex With Vertex The weight between them represents the vertex Opposite Point The impact of location updates, Vertex The position vector of is the normal deviation control factor, Vertex The normal vector of .

[0070] Specifically, the smoothing coefficient Determines the degree of position smoothing. Larger will make the vertex position closer to the average position of neighboring vertices, and smaller Then more information about the original position is retained. Normal deviation control factor It is used to adjust the movement of vertices in the normal direction to correct the surface geometry.

[0071] In summary, the orthopedic 3D printing model construction method based on intelligent AI provided by the present invention has the following technical effects: By collecting and obtaining the user's user database information, an imaging plan is formulated based on the database, and the user's multi-view imaging is performed to generate an image data set, and the image data set is saved as a DICOM format file; a three-dimensional coordinate system is established, the image data set is placed in the coordinate system, and the image coordinates in the three-dimensional coordinate system are used for image registration to form a registration mapping relationship; the image data set is preprocessed, and a bone segmentation operation is performed in the preprocessed image to generate a segmentation result, which has a segmentation confidence mark; the image is fused and reconstructed according to the registration mapping and the segmentation confidence mark to generate a three-dimensional model, and the spatial position complexity of the three-dimensional model is marked; the three-dimensional model is printed and placed to fit, the gravity direction is determined, and the geometric shape analysis is performed based on the gravity direction to determine the preliminary support area; based on the position complexity and the preliminary support area, the support points are optimized and selected, and the selection optimization result is generated; the three-dimensional model is optimized according to the selection optimization result, and finally the user's orthopedic 3D printing model is generated. Thus, the technical effect of improving modeling efficiency and accuracy and improving printing stability is achieved.

[0072] Embodiment 2 Figure 2 : is a schematic diagram of the structure of the orthopedic 3D printing model construction device based on intelligent AI of the present invention. For example, Figure 1 The flowchart of the method for constructing an orthopedic 3D printing model based on intelligent AI in the present invention can be shown as follows: Figure 2 The structure shown is implemented.

[0073] Based on the same concept as the orthopedic 3D printing model construction method based on intelligent AI in the above-mentioned embodiment, the orthopedic 3D printing model construction device based on intelligent AI provided by the present invention includes: The image data acquisition module 11 is used to acquire a user database of a user, configure an image imaging scheme based on the user database, perform multi-view imaging of the user based on the image imaging scheme, establish an image data set, and save the image data set in DICOM format.

[0074] The three-dimensional registration module 12 is used to establish a three-dimensional coordinate system, place the image data set into the three-dimensional coordinate system, perform image registration with the image coordinates in the three-dimensional coordinate system, and establish a registration mapping.

[0075] The skeleton segmentation module 13 is used to perform skeleton segmentation on the preprocessed image data set after preprocessing the image data set, and establish a segmentation result, wherein the segmentation result carries a segmentation confidence mark.

[0076] The fusion reconstruction identification module 14 is used to perform image fusion reconstruction according to the registration map and the segmentation confidence identification, generate a three-dimensional model, and identify the position complexity of the three-dimensional model.

[0077] The placement support module 15 is used to perform printing placement fitting based on the three-dimensional model, determine the gravity direction, perform geometric shape analysis of the three-dimensional model based on the gravity direction, and determine the preliminary support area.

[0078] The support optimization module 16 is used to select and optimize support points based on the position complexity and the preliminary support area, and establish a selection optimization result.

[0079] The entity execution module 17 is used to optimize the three-dimensional model according to the selection optimization result and establish the user's orthopedic 3D printing model.

[0080] The fusion reconstruction identification module 14 includes: The registration mapping weight configuration unit is used to configure the weight according to the registration mapping. The formula is as follows: .

[0081] in, Characterize the registration mapping The weight of the image from each view, Characterization The image quality score of the image from each perspective is Characterization The segmentation confidence level of each view image is Characterizes the number of viewpoints corresponding to the registration map, is the perspective index.

[0082] The pixel fusion unit is used to perform pixel fusion according to the configured weights, as follows: .

[0083] Represents the pixel value after fusion, For the The pixel value of the corresponding position of the perspective image.

[0084] The image fusion reconstruction unit is used to complete the image fusion reconstruction according to the fused pixel values.

[0085] In some implementations, the fusion reconstruction identification module 14 further includes: The fusion data volume extraction and adaptation evaluation unit is used to extract the fusion data volume of image fusion reconstruction, perform adaptation evaluation based on the fusion data volume and the position complexity, and establish an adaptation abnormality mark.

[0086] The additional collection instruction generating unit is used to generate an additional collection instruction based on the adaptation exception identifier.

[0087] The additional data acquisition and fusion reconstruction compensation unit is used to control the imaging device to perform additional data acquisition through the additional acquisition instruction, and perform image fusion reconstruction compensation based on the additional data acquisition result.

[0088] In some embodiments, the support optimization module 16 includes: The support area independence processing unit is used to treat each preliminary support area as an independent area and establish a regional objective function based on the regional information of the preliminary support area. The evaluation characteristics of the regional objective function include the number of support points, materials, stability, and post-processing difficulty.

[0089] The regional evaluation and association establishment unit is used to perform regional evaluation on the independent regions and establish regional associations of the independent regions. The regional associations include regional collaborative associations and regional competitive associations. The regional evaluation includes spatial proximity analysis, mechanical coupling analysis, and material sharing analysis.

[0090] The support point limit constraint and selection optimization unit is used to establish the limit constraint of the support point, configure the solution space with the limit constraint, use the regional objective function as the evaluation function, execute the selection optimization of the support point in the solution space, and perform iterative compensation of the selection optimization through regional association to establish the selection optimization result.

[0091] In some implementations, the support point limit constraint and selection optimization unit in the support optimization module 16 includes: The cooperative grouping and competitive grouping building unit is used to establish cooperative groups and competitive groups based on the area association.

[0092] The joint objective function construction and collaborative grouping optimization unit is used to construct a joint objective function through the regional objective functions corresponding to the collaborative grouping, and to perform joint optimization of the collaborative grouping with the joint objective function.

[0093] The competing group priority sorting unit is used to sort the competing groups in order of priority and establish a sorting result.

[0094] The sequential optimization and iterative compensation unit is used to establish sequential optimization based on the sorting result and complete iterative compensation according to the joint optimization and sequential optimization.

[0095] In some embodiments, the system further comprises: The three-dimensional model fixed-point position recognition unit is used to perform fixed-point position recognition on the three-dimensional model, perform scale division based on the fixed-point position recognition result, and establish M scale division results.

[0096] The spatial scale filtering unit is used to perform spatial scale filtering from a coarse scale to a fine scale based on the M scale division results.

[0097] The filtering fusion and three-dimensional model updating unit is used to perform filtering fusion of each scale division result after all scale division results are filtered, and update the three-dimensional model according to the filtering fusion result.

[0098] In some implementations, the spatial scale filtering unit in the system is used to: The spatial scale filtering is performed through the formula as follows: .

[0099] in, Represents a vertex The new position vector after filtering is Vertex The original position vector, is the smoothing coefficient, Characterizing Vertices The set of adjacent vertices of Characterizing Vertices Any adjacent vertex of Vertex With Vertex The weight between them represents the vertex Opposite Point The impact of location updates, Vertex The position vector of is the normal deviation control factor, Vertex The normal vector of .

[0100] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the aforementioned embodiment one are also applicable to the orthopedic 3D printing model construction device based on intelligent AI described in embodiment two. For the sake of brevity of the specification, they will not be further expanded here.

[0101] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the above-mentioned embodiments. It should be understood that those skilled in the art can still modify the technical solutions recorded in the above-mentioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for constructing an orthopedic 3D printing model based on intelligent AI, characterized in that: The method comprises: Acquire a user database of the user, configure an imaging scheme based on the user database, perform multi-view imaging of the user based on the imaging scheme, establish an image data set, and save the image data set in a DICOM format; Establishing a three-dimensional coordinate system, placing the image data set into the three-dimensional coordinate system, performing image registration with the image coordinates in the three-dimensional coordinate system, and establishing a registration mapping; After preprocessing the image data set, performing bone segmentation of the preprocessed image data set to establish a segmentation result, wherein the segmentation result carries a segmentation confidence mark; Performing image fusion reconstruction according to the registration mapping and the segmentation confidence identifier to generate a three-dimensional model, and identifying the position complexity of the three-dimensional model; Performing printing placement fitting based on the three-dimensional model to determine the direction of gravity, performing geometric shape analysis of the three-dimensional model based on the direction of gravity to determine a preliminary support area; Based on the position complexity and the preliminary support area, the support points are selected and optimized, and the selection and optimization results are established; The three-dimensional model is optimized according to the selection optimization result to establish an orthopedic 3D printing model for the user.

2. The method for constructing an orthopedic 3D printing model based on intelligent AI according to claim 1, characterized in that: The step of selecting and optimizing the support points based on the position complexity and the preliminary support area and establishing the selection and optimization result further includes: Taking each preliminary support area as an independent area, establishing a regional objective function based on the regional information of the preliminary support area, wherein the evaluation characteristics of the regional objective function include the number of support points, material, stability, and post-processing difficulty; Performing regional evaluation on the independent regions, establishing regional associations of the independent regions, wherein the regional associations include regional collaborative associations and regional competitive associations, and the regional evaluation includes spatial proximity analysis, mechanical coupling analysis, and material sharing analysis; Establish limit constraints on support points, configure solution space with the limit constraints, use the regional objective function as an evaluation function, perform selection optimization of support points in the solution space, perform iterative compensation of selection optimization through regional association, and establish selection optimization results.

3. The method for constructing an orthopedic 3D printing model based on intelligent AI as claimed in claim 2, characterized in that: The iterative compensation for selecting and optimizing by regional association also includes: Establishing cooperative groups and competitive groups based on the regional associations; Constructing a joint objective function through the regional objective functions corresponding to the collaborative groups, and performing joint optimization of the collaborative groups with the joint objective function; Sorting the competing groups in order of priority and establishing a sorting result; A sequential optimization is established based on the sorting result, and iterative compensation is completed according to the joint optimization and the sequential optimization.

4. The method for constructing an orthopedic 3D printing model based on intelligent AI according to claim 1, characterized in that: The image fusion reconstruction according to the registration mapping and the segmentation confidence mark also includes: The weights are configured according to the registration map, as follows: ； in, Characterize the registration mapping The weight of the image from each perspective, Characterization The image quality score of the image from each perspective is Characterization The segmentation confidence level of the image from each viewpoint is Characterizes the number of viewpoints corresponding to the registration map, is the perspective index; Pixel fusion is performed according to the configured weights as follows: ； Represents the pixel value after fusion, For the The pixel value of the corresponding position of the perspective image; Image fusion reconstruction is completed based on the fused pixel values.

5. The method for constructing an orthopedic 3D printing model based on intelligent AI according to claim 1, characterized in that: The image fusion reconstruction is performed according to the registration mapping and the segmentation confidence mark to generate a three-dimensional model and mark the position complexity of the three-dimensional model, and further includes: Extracting the amount of fused data of image fusion reconstruction, performing adaptation evaluation based on the amount of fused data and the position complexity, and establishing an adaptation abnormality mark; generating an additional collection instruction based on the adaptation exception identifier; The additional acquisition instruction is used to control the imaging device to perform additional data acquisition, and the additional data acquisition result is used to perform image fusion reconstruction compensation.

6. The method for constructing an orthopedic 3D printing model based on intelligent AI as claimed in claim 5, characterized in that: The method further comprises: Performing fixed-point position recognition on the three-dimensional model, performing scale division based on the fixed-point position recognition result, and establishing M scale division results; Based on the M scale division results, spatial scale filtering from coarse scale to fine scale is performed; After all scale division results are filtered, filtering fusion of each scale division result is performed, and the three-dimensional model is updated according to the filtering fusion results.

7. The method for constructing an orthopedic 3D printing model based on intelligent AI according to claim 6, characterized in that: The spatial scale filtering from a coarse scale to a fine scale based on the M scale division results also includes: The spatial scale filtering is performed through the formula as follows: ； in, Represents a vertex The new position vector after filtering is Vertex The original position vector, is the smoothing coefficient, Characterizing Vertices The set of adjacent vertices of Characterizing Vertices Any adjacent vertex of Vertex With Vertex The weight between them represents the vertex Opposite Point The impact of location updates, Vertex The position vector of is the normal deviation control factor, Vertex The normal vector of .

8. An orthopedic 3D printing model construction device based on intelligent AI, characterized in that: The device is used to execute the method for constructing an orthopedic 3D printing model based on intelligent AI according to any one of claims 1 to 7, and the device comprises: An image data acquisition module, the image data acquisition module is used to acquire a user database of a user, configure an image imaging scheme based on the user database, perform multi-view imaging of the user based on the image imaging scheme, establish an image data set, and save the image data set in DICOM format; A three-dimensional registration module, the three-dimensional registration module is used to establish a three-dimensional coordinate system, place the image data set into the three-dimensional coordinate system, perform image registration with the image coordinates in the three-dimensional coordinate system, and establish a registration mapping; A skeleton segmentation module, wherein the skeleton segmentation module is used to perform skeleton segmentation of the preprocessed image data set after preprocessing the image data set, and establish a segmentation result, wherein the segmentation result carries a segmentation confidence mark; A fusion reconstruction identification module, the fusion reconstruction identification module is used to perform image fusion reconstruction according to the registration map and the segmentation confidence identification, generate a three-dimensional model, and identify the position complexity of the three-dimensional model; A placement support module, the placement support module is used to perform printing placement fitting based on the three-dimensional model, determine the gravity direction, perform geometric shape analysis of the three-dimensional model based on the gravity direction, and determine a preliminary support area; A support optimization module, the support optimization module is used to select and optimize support points based on the position complexity and the preliminary support area, and establish a selection optimization result; The entity execution module is used to optimize the three-dimensional model according to the selection optimization result and establish an orthopedic 3D printing model for the user.

Images